whatmodel.sh / Nous Hermes 2 Mixtral 8x7B DPO

Nous Hermes 2 Mixtral 8x7B DPO

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Nous Hermes 2 Mixtral 8x7B DPO is an open-weights language model from Nous Research, released January 2024. Its published size is 46.7B parameters (12.9B active per token) and a 33k-token context window. Licence: apache-2.0.

Catalogue identity notes

Arena entry 'nous-hermes-2-mixtral-8x7b-dpo' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'nous-hermes-2-mixtral-8x7b-dpo' as 'Nous-Hermes-2-Mixtral-8x7B-DPO' (NousResearch, Apache-2.0), linking https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO. Maker repo NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO @286ae67: licence tag apache-2.0. Parameters: total from the HF safetensors metadata; active 12.9B from Mistral's Mixtral 8x7B announcement (same architecture): 'only uses 12.9B parameters per token'. Released 2024-01: month the maker's Hugging Face repo was created (createdAt 2024-01-11).

40.1±1.8#530 of 719 LLMsfrom 4 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Nous Hermes 2 Mixtral 8x7B DPO, out of 828 with a score, then more from Nous Research.

#modelscorewhereRAMreleased
620Llama3-OpenBioLLM-8B Saama AI Labs40±2local~6.6GB2024-04
621Nous Hermes 2 Mistral 7B DPO Nous Research40±2local~6.1GB2024-02
622Nous Hermes 2 Mixtral 8x7B DPO Nous Research40±2local~31GB2024-01
623Deita 7B v1.0 HKUST NLP40±2local~32GB2023-12
624Code Llama 34B Instruct Meta40±1local~22GB2023-08
more from Nous Research
389Hermes 3 Llama 3.1 405B Nous Research51±1local~114GB2024-08
447Hermes 3 Llama 3.1 70B Nous Research49±1local~44GB2024-07
461Hermes 2 Theta Llama-3 70B Nous Research48±2local~47GB2024-06

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #339 of 393 * · 59% of its score · 2 tests

Beats Gemma 4 E2B, Code Llama 70B Instruct, QwQ-32B-Preview here, though they rank higher overall. Trails Granite 4.0 H 350M, LFM2 350M, Gemma 3 1B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1090.0 ✎▂▁▂▁▃▇█▆▇▄▂▂ beats 41/95avg 1201▇▇▇▇▇▇▇▇▇▇▇▇ 30%blunt
LMArena (text)1164.3 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 46/379avg 1268▇▇▇▇▇▇▇▇▇▇▇▇ 29%blunt
other tests2 not in a task · 40% of its score
testresultvs the others in its rundifficultycountswhy
WildBench v2 WB-Score (task macro)30.7114 WB-Score ✎▁·▁▁·▃█▄▇▆▅▆ beats 17/52avg 45.199 WB-Score▇▇▇▇▇▇▇▇▇▇▇▇▇ 33%sharp
Open PT-LLM Leaderboard average (9 Portuguese tasks)67.2% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 133/276medium · avg 73%▇▇▇ 6.3%at its level · noisy

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run Nous Hermes 2 Mixtral 8x7B DPO · needs ~28.4 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Nous Hermes 2 Mixtral 8x7B DPO · needs ~28.4 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Nous Hermes 2 Mixtral 8x7B DPO · needs ~28.52 GB · from ollama.com
    chat in the terminal
    ollama run nous-hermes2-mixtral:8x7b-dpo-q4_K_M

Official weights and documentation: huggingface.co/NousResearch ↗

$ how the score was worked out · WildBench v2 leaderboard data… 33%, Polyrating: A Cost-Effective… 30%, LMArena leaderboard dataset 29% and 1 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
WildBench v2 leaderboard data (Ai2)1▇▇▇▇▇▇▇▇▇▇ 33%Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇▇▇▇▇▇▇▇▇ 30%CC-BY-4.0
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇ 29%CC BY 4.0
Open Portuguese LLM Leaderboard (archived)1▇▇ 6%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 40.1

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json